Chat
v4.9.7
Install Techstar as an app
Techstar Chat
Generators get pixels and a finished prompt only. Chat LLM writes the words first. Nothing from Venice/Eleven/HF language models.
Pick a track here. This sheet does not pull audio from chat.
Attach in the tray. This sheet does not pull chat history.
Upload here. Results can go to chat. Chat history does not feed this sheet.
Auto: a picture on this sheet is image-to-video. No picture is text-to-video. Both are OpenAI-compatible placeholders (Grok until you point them at your own proxy in Admin).
Image-to-video needs a file on this sheet. Output can go to chat.
Build v4.9.7
Adds this chat to the home screen (PWA). Chrome may hide the sheet if this URL was installed before.
Provider keys, plans, and memory live in Admin. Voices load from ElevenLabs plus the internal list.
Download audio uses the live talk voice unless you pick another later.
TTS model is set in Admin under ElevenLabs. Voices still load live.
Manual Create / Edit does not ask. Auto asks once; a batch of 4 does not ask four times. Retries only run if you turn them on here or the prompt says to keep trying.
Loading limits…
These are the saved endpoints. Each one asks its host for the model list, the same way a normal client does. Keys stay on the server. After SQL is connected, the choice is stored in the database, not in a settings file.
No account needed. Sign in only if you want the free plan.
Plans are no account, free account, and admin. Limits are set in Admin. Say “remember …” in chat to keep a fact.
Style and lyrics go to whatever music host is in config. Cover uses the same box.
T
Chat first when you want ideas. Pictures, songs, and playground tools only run when you pick that action or confirm Auto.
@image1, @image2. Tray keeps attaches until you tap Ă—.You voice is what you typed. Techstar voice is the replies.